cs.LGNov 6, 2026

WearableBridge: Task-Guided Latent Transport for Free-Living Activity Recognition

Authors: Jingjing Zou, Yixin Wang

Organizations: Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego · Department of Statistics, University of Michigan, Ann Arbor

Abstract

Wrist-worn accelerometers make activity monitoring feasible at scale, but incidental arm motion, device orientation, and shifting context blur the signal that separates activities. Calibration studies supply higher-quality references such as concurrent thigh recordings or supervised laboratory wrist sessions, but they are expensive, cover few participants, and are rarely available at deployment. How can limited reference data improve recognition for participants who wear only a wrist device? We propose WearableBridge, which holds the reference encoder and classifier fixed and learns a task-guided transport map, the bridge, that carries each wrist feature into the region the classifier associates with its activity. Reference features or the classifier's predictions indicate the destination, and a classification loss penalizes wrist features that land in the region of another activity. We instantiate WearableBridge with three bridges: Mapper regresses onto reference features, Distillation matches the classifier's class probabilities, and MeanFlow learns a one-step flow from wrist toward reference features. On 40 held-out free-living PAAWS participants, all three bridges improve macro-F1 in every training run, and the strongest, MeanFlow, raises mean macro-F1 from 35.1% to 56.0% with concurrent thigh references (Thigh2Wrist), and from 54.0% to 63.5% with group-matched laboratory wrist references (Lab2Freeliving). Fitted only on PAAWS, MeanFlow also raises macro-F1 on the CAPTURE-24 cohort from 42.8% to 54.7%. The gains replicate on selfBACK, hold across four reference encoders, and grow with temporal context. A study can therefore collect reference recordings for a calibration subset and improve wrist-only recognition for every other participant, training only a bridge of 0.13 to 2.44 million parameters while the reference encoder and classifier stay unchanged.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data

    Mar 11, 2026Prithviraj Tarale, Kiet Chu, Abhishek Varghese +4Human Activity RecognitionSelf-Supervised Time Series Representation Learning

  2. HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound

    May 4, 2026Robin Burchard, Pascal-André Brückner, Marius Bock +2Human Activity RecognitionWearable Sensing

  3. W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition

    Oct 14, 2026Yogesh Prabhu, Loki Natarajan, Jingjing ZouHuman Activity RecognitionRepresentation Learning